Decision trees and transient stability of electric power systems

A general inductive inference method is proposed and applied to the automatic building of decision trees for the transient stability assessment of power systems. On the basis of large sets of simulations, the essential features of the method are analysed and illustrated. Al~lraet-An inductive inference method for the automatic building of decision trees is investigated. Among its various tasks, the splitting and the stop splitting criteria successively applied to the nodes of a grown tree, are found to play a crucial role on its overall shape and performances. The application of this general method to transient stability is systematically explored. Parameters related to the stop splitting criterion, to the learning set and to the tree classes are thus considered, and their influence on the tree features is scrutinized. Evaluation criteria appropriate to assess accuracy are also compared. Various tradeoffs are further examined, such as complexity vs number of classes, or misclassifieation rate vs type of misclassification errors. Possible uses of the trees are also envisaged. Computational issues relating to the building and the use of trees are finally discussed. 1. INTRODUCTION Trm DECISION TREE methodology is nowadays recognized to be a generally nonparametric technique, able to produce classifiers in order to assess new, unseen situations, or to uncover the